Can Agents Spontaneously Form a Society? Introducing a Novel Architecture for Generative Multi-Agents to Elicit Social Emergence

2024/09/10 by H. Zhang, Han‐Zhong Zhang, Jibin Yin +9 · 1 voice · 4 citations
Computer Science · Psychology · Social Sciences · #Action (physics) #Architecture #Feature (linguistics) #Generative grammar #Generative model #Language and cultural evolution #Reinforcement Learning in Robotics #Representation (politics) #Social Robot Interaction and HRI

paper · pdf · doi:10.1145/3746058.3758414

openalex publication_date 2025/09/27 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/31

Abstract

We propose ITCMA-S, a generative agent framework that integrates individual cognition with social reasoning to enable efficient and adaptive behavior.To evaluate it, we introduce the IrollanValley sandbox, a benchmark environment simulating open-ended interactions among identity-less agents.Experiments show that agents equipped with ITCMA-S spontaneously form cliques with internal hierarchies and organize collective actions, demonstrating emergent social structures.

Cited by

• On the Role of Contextual Information and Ego States in LLM Agent Behavior for Transactional Analysis Dialogues
• TACLA: An LLM-Based Multi-Agent Tool for Transactional Analysis Training in Education
• Games Agents Play: Towards Transactional Analysis in LLM-based Multi-Agent Systems
• Simulating Human Behavior with the Psychological-mechanism Agent: Integrating Feeling, Thought, and Action

Discussions

• Can Generative Multi-Agents Spontaneously Form a Society? [hn, 48 points, 5 comments]

Related

• Emergence of Social Norms in Generative Agent Societies: Principles and Architecture
• Spontaneous Emergence of Agent Individuality through Social Interactions in LLM-Based Communities
• AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors
• Generative Agents: Interactive Simulacra of Human Behavior
• Evolving Collective Cognition in Human-Agent Hybrid Societies: How Agents Form Stances and Boundaries